© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14002
    Prev
    Next
    INDEX
    Explanations

    mentions of the heart, prayer, and negative emotional situations.

    oai_token-act-pair · gemini-2.0-flash

    heart

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     heart
    -2.69
    heart
    -2.31
    Heart
    -2.25
     Heart
    -2.19
     HEART
    -1.98
     hearts
    -1.91
    HEART
    -1.88
     corazón
    -1.76
     coração
    -1.66
     cœur
    -1.60
    POSITIVE LOGITS
     Roskov
    0.73
     >=",
    0.70
    ########.
    0.68
     Normdatei
    0.65
    TargetException
    0.64
    unhofer
    0.63
     TestBed
    0.63
    }{*}{
    0.63
     onCancelled
    0.61
     ProtoMessage
    0.60
    Activations Density 2.381%

    No Known Activations